# Micro-splatting: Multistage Isotropy-informed Covariance Regularization Optimization for High-Fidelity 3D Gaussian Splatting

arXiv: https://arxiv.org/abs/2504.05740 · HTML: https://mlsanity.com/paper/2504.05740/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 16 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## Builds on (most cited first, 5 of 5)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Recent Advances in 3D Gaussian Splatting](https://mlsanity.com/paper/2403.11134/) (2024)
- [Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting](https://mlsanity.com/paper/2402.15870/) (2024)

## Built on by (most cited first, 4 of 4)

- [SARA: Scene-Aware Reconstruction Accelerator](https://mlsanity.com/paper/2601.06831/) (2026)
- [Fast and Compact 3D Gaussian Splatting with Polarized Opacity Prior](https://mlsanity.com/paper/2608.22344/) (2026)
- [D3GS: Depth, DINO, and RGB Diffusion Co-Guided 3D Gaussian Splatting for Sparse-View Reconstruction](https://mlsanity.com/paper/2609.22941/) (2026)
- [SPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code](https://mlsanity.com/paper/2610.09116/) (2026)

## Abstract (arXiv)

High-fidelity 3D Gaussian Splatting methods excel at capturing fine textures but often overlook model compactness, resulting in massive splat counts, bloated memory, long training, and complex post-processing. We present Micro-Splatting: Two-Stage Adaptive Growth and Refinement, a unified, in-training pipeline that preserves visual detail while drastically reducing model complexity without any post-processing or auxiliary neural modules. In Stage I (Growth), we introduce a trace-based covariance regularization to maintain near-isotropic Gaussians, mitigating low-pass filtering in high-frequency regions and improving spherical-harmonic color fitting. We then apply gradient-guided adaptive densification that subdivides splats only in visually complex regions, leaving smooth areas sparse. In Stage II (Refinement), we prune low-impact splats using a simple opacity-scale importance score and merge redundant neighbors via lightweight spatial and feature thresholds, producing a lean yet detail-rich model. On four object-centric benchmarks, Micro-Splatting reduces splat count and model size by up to 60% and shortens training by 20%, while matching or surpassing state-of-the-art PSNR, SSIM, and LPIPS in real-time rendering. These results demonstrate that Micro-Splatting delivers both compactness and high fidelity in a single, efficient, end-to-end framework.